ChatSearch: a Dataset and a Generative Retrieval Model for General Conversational Image Retrieval

TL;DR

This paper introduces ChatSearch, a new dataset and generative model for conversational image retrieval, enabling interactive multimodal searches with improved reasoning and knowledge integration.

Contribution

The work presents a novel dataset and a generative retrieval model that advances interactive multimodal image retrieval research.

Findings

ChatSearcher outperforms existing models on the ChatSearch dataset.

The model demonstrates strong reasoning with multimodal context.

The dataset and model facilitate further research in conversational image retrieval.

Abstract

In this paper, we investigate the task of general conversational image retrieval on open-domain images. The objective is to search for images based on interactive conversations between humans and computers. To advance this task, we curate a dataset called ChatSearch. This dataset includes a multi-round multimodal conversational context query for each target image, thereby requiring the retrieval system to find the accurate image from database. Simultaneously, we propose a generative retrieval model named ChatSearcher, which is trained end-to-end to accept/produce interleaved image-text inputs/outputs. ChatSearcher exhibits strong capability in reasoning with multimodal context and can leverage world knowledge to yield visual retrieval results. It demonstrates superior performance on the ChatSearch dataset and also achieves competitive results on other image retrieval tasks and visual conversation tasks. We anticipate that this work will inspire further research on interactive multimodal retrieval systems. Our dataset will be available at https://github.com/joez17/ChatSearch.